lightning monthly heatmap

saturn notebook · generated 2026-05-01 Report Notebook

Overview

Source: /home/coolhand/html/datavis/data_trove/data/natural_hazards/lightning/monthly_heatmap.json

Saturn profiled 59,070 rows across 4 columns. The stats below are deterministic and machine-readable; the prose is a language-model interpretation of those stats (opt-in, added after the fact, never sees raw rows).

[2]:

!pip install saturn-dissect
import subprocess
subprocess.run([
    "saturn", "analyze", "/home/coolhand/html/datavis/data_trove/data/natural_hazards/lightning/monthly_heatmap.json",
    "--findings", "lightning-monthly_heatmap.json",
    "--llm", "anthropic:claude-opus-4-7",
])

Summary confidence: high

This dataset contains 59,070 rows of monthly lightning strike observations, each tagged with latitude, longitude, month, and strike count. Geographically the points sit between roughly 25.35°N–35.46°N and -96.74°W–-79.03°W, suggesting coverage of the southeastern United States. The strikes column is highly skewed (skew ≈ 2.02, max 531 vs. median 34) with a long right tail worth investigating to identify hotspots. Latitude also flags an outlier cluster (about 9.5% of rows), so it is worth checking whether those represent edge regions or data quality issues. Month is evenly bounded 1–12 with a mean near 6.9, hinting at a mild summer concentration in the records.

citing: row_count · columns.lat.stats · columns.lon.stats · columns.strikes.stats · columns.month.stats · columns.lat.alerts · columns.strikes.alerts

Out[4]:

saturn.schema() · 4 columns

column	kind	n	null%	unique	alerts
lat	numeric	59,070	0.0%	868	outliers
lon	numeric	59,070	0.0%	1,231
month	numeric	59,070	0.0%	12
strikes	numeric	59,070	0.0%	381	high_skew

Fig 1.

strikes · Look at the long right tail — most cells have modest counts but a few exceed 500 strikes.

Show data table

Histogram bins for strikes (median: 34.0).
bin	count
1 – 14.25	15261
14.25 – 27.5	9914
27.5 – 40.75	7780
40.75 – 54	6090
54 – 67.25	4959
67.25 – 80.5	3431
80.5 – 93.75	2719
93.75 – 107	2084
107 – 120.2	1684
120.2 – 133.5	1183
133.5 – 146.8	882
146.8 – 160	711
160 – 173.2	578
173.2 – 186.5	414
186.5 – 199.8	320
199.8 – 213	208
213 – 226.2	205
226.2 – 239.5	151
239.5 – 252.8	109
252.8 – 266	84
266 – 279.2	76
279.2 – 292.5	46
292.5 – 305.8	35
305.8 – 319	34
319 – 332.2	34
332.2 – 345.5	23
345.5 – 358.8	11
358.8 – 372	6
372 – 385.2	7
385.2 – 398.5	9
398.5 – 411.8	6
411.8 – 425	3
425 – 438.2	5
438.2 – 451.5	1
451.5 – 464.8	3
464.8 – 478	2
478 – 491.2	0
491.2 – 504.5	0
504.5 – 517.8	0
517.8 – 531	2

Fig 2.

month · Check how observations distribute across the 12 months to spot seasonal concentration.

Show data table

Histogram bins for month (median: 7.0).
bin	count
1 – 1.275	990
1.275 – 1.55	0
1.55 – 1.825	0
1.825 – 2.1	990
2.1 – 2.375	0
2.375 – 2.65	0
2.65 – 2.925	0
2.925 – 3.2	3300
3.2 – 3.475	0
3.475 – 3.75	0
3.75 – 4.025	3300
4.025 – 4.3	0
4.3 – 4.575	0
4.575 – 4.85	0
4.85 – 5.125	6600
5.125 – 5.4	0
5.4 – 5.675	0
5.675 – 5.95	0
5.95 – 6.225	9900
6.225 – 6.5	0
6.5 – 6.775	0
6.775 – 7.05	9900
7.05 – 7.325	0
7.325 – 7.6	0
7.6 – 7.875	0
7.875 – 8.15	9900
8.15 – 8.425	0
8.425 – 8.7	0
8.7 – 8.975	0
8.975 – 9.25	6600
9.25 – 9.525	0
9.525 – 9.8	0
9.8 – 10.08	3300
10.08 – 10.35	0
10.35 – 10.62	0
10.62 – 10.9	0
10.9 – 11.18	3300
11.18 – 11.45	0
11.45 – 11.73	0
11.73 – 12	990

Fig 3.

lat · Inspect the latitude spread (25.35–35.46) and the ~9.5% flagged as outliers.

Show data table

Histogram bins for lat (median: 28.84).
bin	count
25.35 – 25.6	2
25.6 – 25.86	5
25.86 – 26.11	35
26.11 – 26.36	143
26.36 – 26.61	475
26.61 – 26.87	1135
26.87 – 27.12	2153
27.12 – 27.37	3296
27.37 – 27.62	4020
27.62 – 27.88	4062
27.88 – 28.13	4007
28.13 – 28.38	3871
28.38 – 28.64	3643
28.64 – 28.89	3282
28.89 – 29.14	3236
29.14 – 29.39	3215
29.39 – 29.65	3527
29.65 – 29.9	3549
29.9 – 30.15	3239
30.15 – 30.41	2427
30.41 – 30.66	1482
30.66 – 30.91	729
30.91 – 31.16	272
31.16 – 31.42	84
31.42 – 31.67	15
31.67 – 31.92	10
31.92 – 32.17	20
32.17 – 32.43	72
32.43 – 32.68	227
32.68 – 32.93	580
32.93 – 33.19	1045
33.19 – 33.44	1305
33.44 – 33.69	1424
33.69 – 33.94	1167
33.94 – 34.2	762
34.2 – 34.45	343
34.45 – 34.7	166
34.7 – 34.95	34
34.95 – 35.21	5
35.21 – 35.46	6

Fig 4.

lon · See the longitude coverage from -96.74 to -79.03 to confirm the southeastern U.S. footprint.

Show data table

Histogram bins for lon (median: -82.06).
bin	count
-96.74 – -96.3	49
-96.3 – -95.85	343
-95.85 – -95.41	1457
-95.41 – -94.97	2950
-94.97 – -94.53	2653
-94.53 – -94.08	1196
-94.08 – -93.64	275
-93.64 – -93.2	26
-93.2 – -92.76	1
-92.76 – -92.31	0
-92.31 – -91.87	0
-91.87 – -91.43	30
-91.43 – -90.98	226
-90.98 – -90.54	1161
-90.54 – -90.1	3141
-90.1 – -89.66	3520
-89.66 – -89.21	2000
-89.21 – -88.77	592
-88.77 – -88.33	68
-88.33 – -87.88	2
-87.88 – -87.44	0
-87.44 – -87	0
-87 – -86.56	0
-86.56 – -86.11	0
-86.11 – -85.67	1
-85.67 – -85.23	59
-85.23 – -84.79	335
-84.79 – -84.34	1370
-84.34 – -83.9	2386
-83.9 – -83.46	2055
-83.46 – -83.01	799
-83.01 – -82.57	458
-82.57 – -82.13	1836
-82.13 – -81.69	5610
-81.69 – -81.24	9229
-81.24 – -80.8	8753
-80.8 – -80.36	4831
-80.36 – -79.92	1419
-79.92 – -79.47	223
-79.47 – -79.03	16

Fig 5.

Per-column null rate across the corpus. Columns are ordered by input position.

Show data table

Per-column null rate across the corpus.
column	kind	null %
lat	numeric	0.0%
lon	numeric	0.0%
month	numeric	0.0%
strikes	numeric	0.0%

Fig 6.

Pearson correlation across numeric columns (sampled, bounded).

Show data table

Pearson correlation across 4 numeric columns (values clipped to 2 decimals).
	lat	lon	month	strikes
lat	+1.00	-0.37	-0.04	+0.11
lon	-0.37	+1.00	-0.05	-0.07
month	-0.04	-0.05	+1.00	+0.00
strikes	+0.11	-0.07	+0.00	+1.00

lat numeric feature

This is a latitude coordinate column, with all 59070 rows populated across 868 unique values bounded between 25.35 and 35.46 — a span consistent with a regional rather than global footprint. The distribution is right-skewed (skew 1.15) with median 28.84 just below mean 29.23, and roughly 9.5% of points (5626) flag as outliers, suggesting a secondary cluster of locations sitting well north of the main mass around Q1–Q3 (27.84–29.94).

Treatment: Pair with longitude for geospatial joins or binning rather than treating as a standalone scalar feature.

anthropic:claude-opus-4-7 · confidence high

Out[12]:

saturn.columns["lat"].stats

stat	value
n	59,070
nulls	0 (0.0%)
unique	868
min	25.35
max	35.46
mean	29.23
median	28.84
std	1.899
q1	27.84
q3	29.94
iqr	2.1
skew	1.147
kurtosis	0.7033
n_outliers	5,626
outlier_rate	0.09524
zero_rate	0
alert: outliers	9.5% rows beyond 1.5 IQR

Fig 7.

Distribution of lat. Vertical dash marks the median.

Show data table

Histogram bins for lat (median: 28.84).
bin	count
25.35 – 25.6	2
25.6 – 25.86	5
25.86 – 26.11	35
26.11 – 26.36	143
26.36 – 26.61	475
26.61 – 26.87	1135
26.87 – 27.12	2153
27.12 – 27.37	3296
27.37 – 27.62	4020
27.62 – 27.88	4062
27.88 – 28.13	4007
28.13 – 28.38	3871
28.38 – 28.64	3643
28.64 – 28.89	3282
28.89 – 29.14	3236
29.14 – 29.39	3215
29.39 – 29.65	3527
29.65 – 29.9	3549
29.9 – 30.15	3239
30.15 – 30.41	2427
30.41 – 30.66	1482
30.66 – 30.91	729
30.91 – 31.16	272
31.16 – 31.42	84
31.42 – 31.67	15
31.67 – 31.92	10
31.92 – 32.17	20
32.17 – 32.43	72
32.43 – 32.68	227
32.68 – 32.93	580
32.93 – 33.19	1045
33.19 – 33.44	1305
33.44 – 33.69	1424
33.69 – 33.94	1167
33.94 – 34.2	762
34.2 – 34.45	343
34.45 – 34.7	166
34.7 – 34.95	34
34.95 – 35.21	5
35.21 – 35.46	6

lon numeric feature

Longitude coordinates, all negative and tightly bounded between -96.74 and -79.03, placing every record in the eastern half of North America. The distribution is left-skewed (skew -0.85) with a median of -82.06, suggesting a concentration toward the eastern edge of that range and a longer tail westward. With only 1,231 unique values across 59,070 rows, coordinates are heavily repeated, hinting at a fixed set of locations rather than continuous GPS readings.

Treatment: Pair with lat as a geospatial feature; consider binning or joining to a place identifier given the low cardinality.

anthropic:claude-opus-4-7 · confidence high

Out[15]:

saturn.columns["lon"].stats

stat	value
n	59,070
nulls	0 (0.0%)
unique	1,231
min	-96.74
max	-79.03
mean	-85.27
median	-82.06
std	5.252
q1	-89.94
q3	-81.22
iqr	8.72
skew	-0.8513
kurtosis	-0.8532
n_outliers	0
outlier_rate	0
zero_rate	0

Fig 8.

Distribution of lon. Vertical dash marks the median.

Show data table

Histogram bins for lon (median: -82.06).
bin	count
-96.74 – -96.3	49
-96.3 – -95.85	343
-95.85 – -95.41	1457
-95.41 – -94.97	2950
-94.97 – -94.53	2653
-94.53 – -94.08	1196
-94.08 – -93.64	275
-93.64 – -93.2	26
-93.2 – -92.76	1
-92.76 – -92.31	0
-92.31 – -91.87	0
-91.87 – -91.43	30
-91.43 – -90.98	226
-90.98 – -90.54	1161
-90.54 – -90.1	3141
-90.1 – -89.66	3520
-89.66 – -89.21	2000
-89.21 – -88.77	592
-88.77 – -88.33	68
-88.33 – -87.88	2
-87.88 – -87.44	0
-87.44 – -87	0
-87 – -86.56	0
-86.56 – -86.11	0
-86.11 – -85.67	1
-85.67 – -85.23	59
-85.23 – -84.79	335
-84.79 – -84.34	1370
-84.34 – -83.9	2386
-83.9 – -83.46	2055
-83.46 – -83.01	799
-83.01 – -82.57	458
-82.57 – -82.13	1836
-82.13 – -81.69	5610
-81.69 – -81.24	9229
-81.24 – -80.8	8753
-80.8 – -80.36	4831
-80.36 – -79.92	1419
-79.92 – -79.47	223
-79.47 – -79.03	16

month numeric feature

This is a calendar month encoded as an integer 1–12, with all 12 values present across 59,070 rows and no nulls. The distribution leans slightly toward the second half of the year (mean 6.90, median 7) but is essentially flat (kurtosis -0.21, skew -0.15) with no outliers.

Treatment: Treat as a cyclical categorical (e.g., sine/cosine encode) rather than a raw numeric.

anthropic:claude-opus-4-7 · confidence high

Out[18]:

saturn.columns["month"].stats

stat	value
n	59,070
nulls	0 (0.0%)
unique	12
min	1
max	12
mean	6.899
median	7
std	2.335
q1	5
q3	8
iqr	3
skew	-0.155
kurtosis	-0.2056
n_outliers	0
outlier_rate	0
zero_rate	0

Fig 9.

Distribution of month. Vertical dash marks the median.

Show data table

Histogram bins for month (median: 7.0).
bin	count
1 – 1.275	990
1.275 – 1.55	0
1.55 – 1.825	0
1.825 – 2.1	990
2.1 – 2.375	0
2.375 – 2.65	0
2.65 – 2.925	0
2.925 – 3.2	3300
3.2 – 3.475	0
3.475 – 3.75	0
3.75 – 4.025	3300
4.025 – 4.3	0
4.3 – 4.575	0
4.575 – 4.85	0
4.85 – 5.125	6600
5.125 – 5.4	0
5.4 – 5.675	0
5.675 – 5.95	0
5.95 – 6.225	9900
6.225 – 6.5	0
6.5 – 6.775	0
6.775 – 7.05	9900
7.05 – 7.325	0
7.325 – 7.6	0
7.6 – 7.875	0
7.875 – 8.15	9900
8.15 – 8.425	0
8.425 – 8.7	0
8.7 – 8.975	0
8.975 – 9.25	6600
9.25 – 9.525	0
9.525 – 9.8	0
9.8 – 10.08	3300
10.08 – 10.35	0
10.35 – 10.62	0
10.62 – 10.9	0
10.9 – 11.18	3300
11.18 – 11.45	0
11.45 – 11.73	0
11.73 – 12	990

strikes numeric feature

A non-negative integer count called 'strikes' with 381 distinct values across 59,070 rows and no nulls or zeros, ranging from 1 to 531 with a median of 34 and mean of 49.4. The distribution is heavily right-skewed (skew 2.02, kurtosis 6.09) and the standard deviation (49.8) roughly equals the mean, with 2,917 outliers (4.9%) extending the upper tail well past the Q3 of 68.

Treatment: Apply a log or sqrt transform before modelling to tame the right skew.

anthropic:claude-opus-4-7 · confidence high

Out[21]:

saturn.columns["strikes"].stats

stat	value
n	59,070
nulls	0 (0.0%)
unique	381
min	1
max	531
mean	49.43
median	34
std	49.83
q1	14
q3	68
iqr	54
skew	2.023
kurtosis	6.094
n_outliers	2,917
outlier_rate	0.04938
zero_rate	0
alert: high_skew	skew=+2.02

Fig 10.

Distribution of strikes. Vertical dash marks the median.

Show data table

Histogram bins for strikes (median: 34.0).
bin	count
1 – 14.25	15261
14.25 – 27.5	9914
27.5 – 40.75	7780
40.75 – 54	6090
54 – 67.25	4959
67.25 – 80.5	3431
80.5 – 93.75	2719
93.75 – 107	2084
107 – 120.2	1684
120.2 – 133.5	1183
133.5 – 146.8	882
146.8 – 160	711
160 – 173.2	578
173.2 – 186.5	414
186.5 – 199.8	320
199.8 – 213	208
213 – 226.2	205
226.2 – 239.5	151
239.5 – 252.8	109
252.8 – 266	84
266 – 279.2	76
279.2 – 292.5	46
292.5 – 305.8	35
305.8 – 319	34
319 – 332.2	34
332.2 – 345.5	23
345.5 – 358.8	11
358.8 – 372	6
372 – 385.2	7
385.2 – 398.5	9
398.5 – 411.8	6
411.8 – 425	3
425 – 438.2	5
438.2 – 451.5	1
451.5 – 464.8	3
464.8 – 478	2
478 – 491.2	0
491.2 – 504.5	0
504.5 – 517.8	0
517.8 – 531	2

How to cite

click to copy

BibTeX

@misc{saturn-lightning-monthly-heatmap-2026,
  author       = {Steuber, Luke},
  title        = {Saturn reading: lightning monthly heatmap},
  year         ={2026},
  howpublished = {\url{https://dr.eamer.dev/saturn/view/lightning-monthly_heatmap}},
  note         = {Profiled with saturn-dissect v0.2.0, prompt saturn-insight-v2, model anthropic:claude-opus-4-7},
}

APA

Steuber, L. (2026). Saturn reading: lightning monthly heatmap. Source: /home/coolhand/html/datavis/data_trove/data/natural_hazards/lightning/monthly_heatmap.json. Profiled with saturn-dissect v0.2.0 (saturn-insight-v2, anthropic:claude-opus-4-7). Retrieved from https://dr.eamer.dev/saturn/view/lightning-monthly_heatmap